发表机构
University of Michigan, Ann Arbor（密歇根大学安娜堡分校）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
Pimento框架将文本语料、查询和隐私策略转化为关系数据库，结合CI与DP，通过DP/CI感知的Text-to-SQL及情境差分隐私，实现端到端隐私保证并提升查询效用，在基准上75.3%选优且零泄露。
AI 中文摘要
目前，存在两种最先进的互补性隐私保证：情境完整性（CI）用于规定哪些信息可以流动，以及差分隐私（DP）用于规定哪些信息可以被推断。然而，这两种保证都无法直接映射到自然语言上，导致现有方法无法为非结构化文本的分析提供这些保证。我们通过Pimento框架解决了这一差距，该框架接受三种形式的自然语言：文本语料库、查询和隐私策略；并将它们转化为关系数据库，创建一个共同的底层基础，在此之上可以正式地强制执行这两种保证。通过这种设计，我们不仅提供了端到端的隐私保证，还通过三项关键贡献提升了效用：DP感知的Text-to-SQL，它搜索需要最少DP噪声的正确查询；CI感知的Text-to-SQL，它将自然语言策略编译为数据库上可执行的CI规则；以及我们提出的新的隐私定义——情境差分隐私，它在CI下重新定义了传统的DP邻域，并产生更紧密的平滑敏感度界限。在新的基准测试中，Pimento在75.3%的情况下选择了最佳查询（比基线高出最多45个百分点），并在正确的策略落地情况下实现了零泄露。据我们所知，Pimento是第一个在CI、DP及其组合下为自然语言分析提供正式隐私保证的框架。
英文摘要
Currently, there are two state-of-the-art, complementary privacy guarantees: contextual integrity (CI) for what may flow, and differential privacy (DP) for what may be inferred. Yet neither maps cleanly onto natural language, leaving existing approaches unable to provide these guarantees for analytics over unstructured text. We address this gap with Pimento, a framework that takes three forms of natural language: text corpus, queries, and privacy policies; and grounds them into a relational database, creating a common substrate on which both guarantees can be enforced formally. With this design, we not only provide end to end privacy guarantees, but also improvement to utility through three key contributions: DP aware Text-to-SQL, which searches for correct queries requiring the least DP noise; CI aware Text-to-SQL, which compiles natural language policies into executable CI rules over the database; and a new privacy definition we call contextual differential privacy, which redefines the traditional DP neighborhood under CI, and yields a tighter smooth sensitivity bound. Across new benchmarks, Pimento selects the best query in 75.3% of cases (upto +45 points over baselines) and achieves zero leakage under correct policy grounding. To our knowledge, Pimento is the first framework to provide formal privacy guarantees for natural language analytics under CI, DP, and their composition.
